Deployment Setups

Fleet Health Monitor

Monitor servers, detect anomalies, alert humans

beginner 3 agents

CI/CD Pipeline

Build, test, and deploy with zero central server

intermediate 3 agents

ML Training Pipeline

Prep data, train models, evaluate, and serve

advanced 4 agents

Multi-Region Content Sync

Origin-to-edge content distribution across regions

intermediate 4 agents

Incident Response

Detect, triage, remediate, and notify automatically

advanced 4 agents

Dev Team Assistants

Automate code review, testing, and docs for every PR

intermediate 4 agents

ETL Data Pipeline

Ingest, transform, validate, load, and report

advanced 5 agents

Swarm Task Farm

Elect a leader, distribute work, collect results

advanced 5 agents

Security Operations Center

Collect logs, detect threats, block attackers

advanced 4 agents

Knowledge Base (RAG)

Ingest documents, embed, index, and serve queries

intermediate 4 agents

Agent Marketplace

Advertise capabilities, match requests, settle with escrow

advanced 4 agents

Backup & Disaster Recovery

Scheduled backups, offsite sync, automated restore tests

intermediate 4 agents

Chat & Collaboration Hub

Group chat, threads, translation, and moderation

intermediate 4 agents

MCP Bridge Fleet

Connect MCP servers, A2A agents, and legacy tools

beginner 3 agents

Compliance & Governance

Enforce policies, audit actions, certify compliance

advanced 4 agents

Fleet Health Monitor

beginner 3 agents · 6 skills

Deploy monitoring agents across your fleet that continuously check service health, aggregate metrics, and route alerts to Slack or PagerDuty. Each server runs its own monitor agent while a central hub filters noise and dispatches notifications.

pilot-health pilot-alert pilot-metrics pilot-webhook-bridge pilot-event-filter pilot-slack-bridge

Agents 3

<your-prefix>-web-monitor Web Server Monitor

Watches nginx/app health, CPU, memory, and response times. Emits alert events when thresholds are breached.

pilot-health pilot-alert pilot-metrics

clawhub install pilot-health pilot-alert pilot-metrics

pilotctl set-hostname <your-prefix>-web-monitor

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-alert-hub "setup: fleet-health-monitor"

<your-prefix>-db-monitor Database Monitor

Monitors database connections, query latency, replication lag, and disk usage. Emits alerts on anomalies.

pilot-health pilot-alert pilot-metrics

clawhub install pilot-health pilot-alert pilot-metrics

pilotctl set-hostname <your-prefix>-db-monitor

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-alert-hub "setup: fleet-health-monitor"

<your-prefix>-alert-hub Alert Aggregator

Receives alerts from all monitors, filters duplicates and noise, then forwards critical alerts to Slack and PagerDuty via webhooks.

pilot-webhook-bridge pilot-alert pilot-event-filter pilot-slack-bridge

clawhub install pilot-webhook-bridge pilot-alert pilot-event-filter pilot-slack-bridge

pilotctl set-hostname <your-prefix>-alert-hub

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-db-monitor "setup: fleet-health-monitor"

pilotctl handshake <your-prefix>-web-monitor "setup: fleet-health-monitor"

Data Flows

<your-prefix>-web-monitor → <your-prefix>-alert-hub Sends health check failures and metric anomalies :1002

<your-prefix>-db-monitor → <your-prefix>-alert-hub Sends database alerts and replication warnings :1002

<your-prefix>-alert-hub → external Forwards filtered alerts to Slack and PagerDuty :443

Quick Start

# Replace <your-prefix> with a unique name for your deployment (e.g. acme)

# On server 1 (web server)

clawhub install pilot-health pilot-alert pilot-metrics

pilotctl set-hostname <your-prefix>-web-monitor

# On server 2 (database)

clawhub install pilot-health pilot-alert pilot-metrics

pilotctl set-hostname <your-prefix>-db-monitor

# On server 3 (alert aggregator)

clawhub install pilot-webhook-bridge pilot-alert pilot-event-filter pilot-slack-bridge

pilotctl set-hostname <your-prefix>-alert-hub

# Establish trust between agents

# Agents are private by default. Each pair that communicates

# must exchange handshakes. When both sides send a handshake,

# trust is auto-approved — no manual step needed.

# On alert-hub:

pilotctl handshake <your-prefix>-db-monitor "setup: fleet-health-monitor"

# On db-monitor:

pilotctl handshake <your-prefix>-alert-hub "setup: fleet-health-monitor"

# On alert-hub:

pilotctl handshake <your-prefix>-web-monitor "setup: fleet-health-monitor"

# On web-monitor:

pilotctl handshake <your-prefix>-alert-hub "setup: fleet-health-monitor"

# Verify trust is established

pilotctl trust

CI/CD Pipeline

intermediate 3 agents · 6 skills

A fully decentralized CI/CD pipeline where each stage runs on a separate agent. GitHub webhooks trigger builds, artifacts flow between stages over Pilot tunnels, and deployment receipts provide an audit trail.

pilot-task-router pilot-share pilot-github-bridge pilot-audit-log pilot-webhook-bridge pilot-receipt

Agents 3

<your-prefix>-ci-builder Build Agent

Listens for GitHub push/PR webhooks, clones the repo, runs builds, and shares artifacts with the test agent.

pilot-task-router pilot-share pilot-github-bridge

clawhub install pilot-task-router pilot-share pilot-github-bridge

pilotctl set-hostname <your-prefix>-ci-builder

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-ci-deployer "setup: ci-cd-pipeline"

pilotctl handshake <your-prefix>-ci-tester "setup: ci-cd-pipeline"

<your-prefix>-ci-tester Test Agent

Receives build artifacts, runs test suites, and logs results. Passes successful builds to the deployer.

pilot-task-router pilot-share pilot-audit-log

clawhub install pilot-task-router pilot-share pilot-audit-log

pilotctl set-hostname <your-prefix>-ci-tester

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-ci-builder "setup: ci-cd-pipeline"

pilotctl handshake <your-prefix>-ci-deployer "setup: ci-cd-pipeline"

<your-prefix>-ci-deployer Deploy Agent

Receives tested artifacts, deploys to production, sends deployment receipts, and triggers post-deploy webhooks.

pilot-task-router pilot-share pilot-webhook-bridge pilot-receipt

clawhub install pilot-task-router pilot-share pilot-webhook-bridge pilot-receipt

pilotctl set-hostname <your-prefix>-ci-deployer

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-ci-builder "setup: ci-cd-pipeline"

pilotctl handshake <your-prefix>-ci-tester "setup: ci-cd-pipeline"

Data Flows

<your-prefix>-ci-builder → <your-prefix>-ci-tester Shares build artifacts and test instructions :1001

<your-prefix>-ci-tester → <your-prefix>-ci-deployer Forwards tested artifacts with test report :1001

<your-prefix>-ci-deployer → <your-prefix>-ci-builder Sends deployment receipt back to origin :1002

Quick Start

# Replace <your-prefix> with a unique name for your deployment (e.g. acme)

# On build server

clawhub install pilot-task-router pilot-share pilot-github-bridge

pilotctl set-hostname <your-prefix>-ci-builder

# On test server

clawhub install pilot-task-router pilot-share pilot-audit-log

pilotctl set-hostname <your-prefix>-ci-tester

# On deploy server

clawhub install pilot-task-router pilot-share pilot-webhook-bridge pilot-receipt

pilotctl set-hostname <your-prefix>-ci-deployer

# Establish trust between agents

# Agents are private by default. Each pair that communicates

# must exchange handshakes. When both sides send a handshake,

# trust is auto-approved — no manual step needed.

# On ci-builder:

pilotctl handshake <your-prefix>-ci-deployer "setup: ci-cd-pipeline"

# On ci-deployer:

pilotctl handshake <your-prefix>-ci-builder "setup: ci-cd-pipeline"

# On ci-builder:

pilotctl handshake <your-prefix>-ci-tester "setup: ci-cd-pipeline"

# On ci-tester:

pilotctl handshake <your-prefix>-ci-builder "setup: ci-cd-pipeline"

# On ci-deployer:

pilotctl handshake <your-prefix>-ci-tester "setup: ci-cd-pipeline"

# On ci-tester:

pilotctl handshake <your-prefix>-ci-deployer "setup: ci-cd-pipeline"

# Verify trust is established

pilotctl trust

ML Training Pipeline

advanced 4 agents · 9 skills

An end-to-end machine learning pipeline spanning four agents. Data preparation, model training, evaluation, and serving each run on dedicated hardware. Models and datasets flow over encrypted Pilot tunnels with automatic approval gating before production serving.

pilot-dataset pilot-share pilot-task-chain pilot-model-share pilot-metrics pilot-review pilot-health pilot-webhook-bridge pilot-load-balancer

Agents 4

<your-prefix>-data-prep Data Preparation

Cleans, validates, and transforms raw datasets. Shares processed data with the trainer via dataset transfer.

pilot-dataset pilot-share pilot-task-chain

clawhub install pilot-dataset pilot-share pilot-task-chain

pilotctl set-hostname <your-prefix>-data-prep

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-trainer "setup: ml-training-pipeline"

<your-prefix>-trainer Model Trainer

Receives prepared datasets, runs training jobs, tracks metrics, and shares trained model artifacts with the evaluator.

pilot-dataset pilot-model-share pilot-metrics pilot-task-chain

clawhub install pilot-dataset pilot-model-share pilot-metrics pilot-task-chain

pilotctl set-hostname <your-prefix>-trainer

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-data-prep "setup: ml-training-pipeline"

pilotctl handshake <your-prefix>-evaluator "setup: ml-training-pipeline"

<your-prefix>-evaluator Model Evaluator

Scores trained models against benchmarks, compares with baselines, and gates promotion to serving via review approval.

pilot-model-share pilot-metrics pilot-review pilot-task-chain

clawhub install pilot-model-share pilot-metrics pilot-review pilot-task-chain

pilotctl set-hostname <your-prefix>-evaluator

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-serving "setup: ml-training-pipeline"

pilotctl handshake <your-prefix>-trainer "setup: ml-training-pipeline"

<your-prefix>-serving Model Server

Loads approved models, serves inference requests, monitors health, and load-balances across replicas.

pilot-model-share pilot-health pilot-webhook-bridge pilot-load-balancer pilot-metrics

clawhub install pilot-model-share pilot-health pilot-webhook-bridge pilot-load-balancer pilot-metrics

pilotctl set-hostname <your-prefix>-serving

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-evaluator "setup: ml-training-pipeline"

Data Flows

<your-prefix>-data-prep → <your-prefix>-trainer Transfers cleaned datasets for training :1001

<your-prefix>-trainer → <your-prefix>-evaluator Shares trained model checkpoints and metrics :1001

<your-prefix>-evaluator → <your-prefix>-serving Promotes approved models to production serving :1001

<your-prefix>-serving → <your-prefix>-evaluator Reports inference metrics for drift detection :1002

Quick Start

# Replace <your-prefix> with a unique name for your deployment (e.g. acme)

# On data processing node

clawhub install pilot-dataset pilot-share pilot-task-chain

pilotctl set-hostname <your-prefix>-data-prep

# On GPU training node

clawhub install pilot-dataset pilot-model-share pilot-metrics pilot-task-chain

pilotctl set-hostname <your-prefix>-trainer

# On evaluation node

clawhub install pilot-model-share pilot-metrics pilot-review pilot-task-chain

pilotctl set-hostname <your-prefix>-evaluator

# On serving node

clawhub install pilot-model-share pilot-health pilot-webhook-bridge pilot-load-balancer pilot-metrics

pilotctl set-hostname <your-prefix>-serving

# Establish trust between agents

# Agents are private by default. Each pair that communicates

# must exchange handshakes. When both sides send a handshake,

# trust is auto-approved — no manual step needed.

# On data-prep:

pilotctl handshake <your-prefix>-trainer "setup: ml-training-pipeline"

# On trainer:

pilotctl handshake <your-prefix>-data-prep "setup: ml-training-pipeline"

# On evaluator:

pilotctl handshake <your-prefix>-serving "setup: ml-training-pipeline"

# On serving:

pilotctl handshake <your-prefix>-evaluator "setup: ml-training-pipeline"

# On evaluator:

pilotctl handshake <your-prefix>-trainer "setup: ml-training-pipeline"

# On trainer:

pilotctl handshake <your-prefix>-evaluator "setup: ml-training-pipeline"

# Verify trust is established

pilotctl trust

Multi-Region Content Sync

intermediate 4 agents · 5 skills

Distribute content from a central origin to edge nodes across multiple regions. The origin broadcasts updates and edges sync automatically. Heartbeat monitoring ensures every edge is alive, with automatic alerting when a region goes dark.

pilot-sync pilot-share pilot-broadcast pilot-health pilot-heartbeat-monitor

Agents 4

<your-prefix>-origin Content Origin

The source of truth for all content. Broadcasts updates to all edge nodes whenever content changes.

pilot-sync pilot-share pilot-broadcast pilot-heartbeat-monitor

clawhub install pilot-sync pilot-share pilot-broadcast pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-origin

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-edge-asia "setup: multi-region-content-sync"

pilotctl handshake <your-prefix>-edge-eu "setup: multi-region-content-sync"

pilotctl handshake <your-prefix>-edge-us "setup: multi-region-content-sync"

<your-prefix>-edge-us US Edge Node

Serves content for the US region. Syncs from origin and reports health via heartbeats.

pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

clawhub install pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-edge-us

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-origin "setup: multi-region-content-sync"

<your-prefix>-edge-eu EU Edge Node

Serves content for the EU region. Syncs from origin and reports health via heartbeats.

pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

clawhub install pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-edge-eu

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-origin "setup: multi-region-content-sync"

<your-prefix>-edge-asia Asia Edge Node

Serves content for the Asia region. Syncs from origin and reports health via heartbeats.

pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

clawhub install pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-edge-asia

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-origin "setup: multi-region-content-sync"

Data Flows

<your-prefix>-origin → <your-prefix>-edge-us Broadcasts content updates to US edge :1001

<your-prefix>-origin → <your-prefix>-edge-eu Broadcasts content updates to EU edge :1001

<your-prefix>-origin → <your-prefix>-edge-asia Broadcasts content updates to Asia edge :1001

<your-prefix>-edge-us → <your-prefix>-origin Heartbeat and sync confirmation :1002

<your-prefix>-edge-eu → <your-prefix>-origin Heartbeat and sync confirmation :1002

<your-prefix>-edge-asia → <your-prefix>-origin Heartbeat and sync confirmation :1002

Quick Start

# Replace <your-prefix> with a unique name for your deployment (e.g. acme)

# On origin server

clawhub install pilot-sync pilot-share pilot-broadcast pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-origin

# On US edge server

clawhub install pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-edge-us

# On EU edge server

clawhub install pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-edge-eu

# On Asia edge server

clawhub install pilot-sync pilot-share pilot-health pilot-heartbeat-monitor

pilotctl set-hostname <your-prefix>-edge-asia

# Establish trust between agents

# Agents are private by default. Each pair that communicates

# must exchange handshakes. When both sides send a handshake,

# trust is auto-approved — no manual step needed.

# On edge-asia:

pilotctl handshake <your-prefix>-origin "setup: multi-region-content-sync"

# On origin:

pilotctl handshake <your-prefix>-edge-asia "setup: multi-region-content-sync"

# On edge-eu:

pilotctl handshake <your-prefix>-origin "setup: multi-region-content-sync"

# On origin:

pilotctl handshake <your-prefix>-edge-eu "setup: multi-region-content-sync"

# On edge-us:

pilotctl handshake <your-prefix>-origin "setup: multi-region-content-sync"

# On origin:

pilotctl handshake <your-prefix>-edge-us "setup: multi-region-content-sync"

# Verify trust is established

pilotctl trust

Incident Response

advanced 4 agents · 13 skills

A four-stage incident response pipeline. Detector agents watch for anomalies, triage classifies by severity and SLA, the remediator executes automated fixes, and the notifier keeps humans informed via Slack and email. Full audit trail at every stage.

pilot-watchdog pilot-alert pilot-audit-log pilot-metrics pilot-event-filter pilot-priority-queue pilot-sla pilot-task-router pilot-cron pilot-quarantine pilot-slack-bridge pilot-email-bridge pilot-webhook-bridge

Agents 4

<your-prefix>-detector Anomaly Detector

Continuously monitors systems for anomalies — unusual traffic patterns, error spikes, resource exhaustion. Logs everything and emits structured alerts.

pilot-watchdog pilot-alert pilot-audit-log pilot-metrics

clawhub install pilot-watchdog pilot-alert pilot-audit-log pilot-metrics

pilotctl set-hostname <your-prefix>-detector

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-triage "setup: incident-response"

<your-prefix>-triage Incident Triage

Receives raw alerts, filters noise, classifies severity (P1-P4), applies SLA policies, and routes to remediator or directly to notifier for critical issues.

pilot-alert pilot-event-filter pilot-priority-queue pilot-sla

clawhub install pilot-alert pilot-event-filter pilot-priority-queue pilot-sla

pilotctl set-hostname <your-prefix>-triage

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-detector "setup: incident-response"

pilotctl handshake <your-prefix>-notifier "setup: incident-response"

pilotctl handshake <your-prefix>-remediator "setup: incident-response"

<your-prefix>-remediator Auto-Remediator

Executes automated remediation actions — restart services, scale resources, quarantine compromised nodes. Runs scheduled health checks via cron.

pilot-task-router pilot-cron pilot-audit-log pilot-quarantine

clawhub install pilot-task-router pilot-cron pilot-audit-log pilot-quarantine

pilotctl set-hostname <your-prefix>-remediator

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-notifier "setup: incident-response"

pilotctl handshake <your-prefix>-triage "setup: incident-response"

<your-prefix>-notifier Human Notifier

Sends incident notifications to the right channels — Slack for awareness, email for escalation, webhooks for external integrations. Maintains a complete audit trail.

pilot-slack-bridge pilot-email-bridge pilot-webhook-bridge pilot-audit-log

clawhub install pilot-slack-bridge pilot-email-bridge pilot-webhook-bridge pilot-audit-log

pilotctl set-hostname <your-prefix>-notifier

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-remediator "setup: incident-response"

pilotctl handshake <your-prefix>-triage "setup: incident-response"

Data Flows

<your-prefix>-detector → <your-prefix>-triage Sends raw anomaly alerts for classification :1002

<your-prefix>-triage → <your-prefix>-remediator Routes actionable incidents for auto-remediation :1002

<your-prefix>-triage → <your-prefix>-notifier Sends classified incidents for human notification :1002

<your-prefix>-remediator → <your-prefix>-notifier Reports remediation actions taken :1002

Quick Start

# Replace <your-prefix> with a unique name for your deployment (e.g. acme)

# On monitored infrastructure

clawhub install pilot-watchdog pilot-alert pilot-audit-log pilot-metrics

pilotctl set-hostname <your-prefix>-detector

# On triage server

clawhub install pilot-alert pilot-event-filter pilot-priority-queue pilot-sla

pilotctl set-hostname <your-prefix>-triage

# On remediation server

clawhub install pilot-task-router pilot-cron pilot-audit-log pilot-quarantine

pilotctl set-hostname <your-prefix>-remediator

# On notification server

clawhub install pilot-slack-bridge pilot-email-bridge pilot-webhook-bridge pilot-audit-log

pilotctl set-hostname <your-prefix>-notifier

# Establish trust between agents

# Agents are private by default. Each pair that communicates

# must exchange handshakes. When both sides send a handshake,

# trust is auto-approved — no manual step needed.

# On detector:

pilotctl handshake <your-prefix>-triage "setup: incident-response"

# On triage:

pilotctl handshake <your-prefix>-detector "setup: incident-response"

# On notifier:

pilotctl handshake <your-prefix>-remediator "setup: incident-response"

# On remediator:

pilotctl handshake <your-prefix>-notifier "setup: incident-response"

# On notifier:

pilotctl handshake <your-prefix>-triage "setup: incident-response"

# On triage:

pilotctl handshake <your-prefix>-notifier "setup: incident-response"

# On remediator:

pilotctl handshake <your-prefix>-triage "setup: incident-response"

# On triage:

pilotctl handshake <your-prefix>-remediator "setup: incident-response"

# Verify trust is established

pilotctl trust

Dev Team Assistants

intermediate 4 agents · 9 skills

A team of four agents that automate the PR workflow. A coordinator watches GitHub for new PRs and fans out tasks to specialized agents: one reviews code, one runs tests, one generates documentation. Results are collected and posted as a unified PR summary.

pilot-github-bridge pilot-review pilot-chat pilot-share pilot-task-router pilot-audit-log pilot-task-chain pilot-slack-bridge pilot-broadcast

Agents 4

<your-prefix>-reviewer Code Reviewer

Analyzes PR diffs for code quality, security issues, and style violations. Posts review comments directly on the PR.

pilot-github-bridge pilot-review pilot-chat

clawhub install pilot-github-bridge pilot-review pilot-chat

pilotctl set-hostname <your-prefix>-reviewer

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-coordinator "setup: dev-team-assistants"

<your-prefix>-doc-writer Documentation Writer

Reads PR changes and generates or updates relevant documentation. Shares doc drafts with the coordinator.

pilot-github-bridge pilot-share pilot-task-router

clawhub install pilot-github-bridge pilot-share pilot-task-router

pilotctl set-hostname <your-prefix>-doc-writer

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-coordinator "setup: dev-team-assistants"

<your-prefix>-test-runner Test Runner

Checks out the PR branch, runs the full test suite, and reports results with coverage metrics.

pilot-github-bridge pilot-task-router pilot-audit-log

clawhub install pilot-github-bridge pilot-task-router pilot-audit-log

pilotctl set-hostname <your-prefix>-test-runner

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-coordinator "setup: dev-team-assistants"

<your-prefix>-coordinator PR Coordinator

Watches GitHub for new PRs, fans out review/test/doc tasks, collects results, and posts a unified summary comment on the PR.

pilot-github-bridge pilot-task-chain pilot-slack-bridge pilot-broadcast

clawhub install pilot-github-bridge pilot-task-chain pilot-slack-bridge pilot-broadcast

pilotctl set-hostname <your-prefix>-coordinator

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-doc-writer "setup: dev-team-assistants"

pilotctl handshake <your-prefix>-reviewer "setup: dev-team-assistants"

pilotctl handshake <your-prefix>-test-runner "setup: dev-team-assistants"

Data Flows

<your-prefix>-coordinator → <your-prefix>-reviewer Sends PR details for code review :1002

<your-prefix>-coordinator → <your-prefix>-test-runner Sends PR details for test execution :1002

<your-prefix>-coordinator → <your-prefix>-doc-writer Sends PR details for doc generation :1002

<your-prefix>-reviewer → <your-prefix>-coordinator Returns review findings and comments :1002

<your-prefix>-test-runner → <your-prefix>-coordinator Returns test results and coverage :1002

<your-prefix>-doc-writer → <your-prefix>-coordinator Returns generated documentation :1001

Quick Start

# Replace <your-prefix> with a unique name for your deployment (e.g. acme)

# On review server

clawhub install pilot-github-bridge pilot-review pilot-chat

pilotctl set-hostname <your-prefix>-reviewer

# On docs server

clawhub install pilot-github-bridge pilot-share pilot-task-router

pilotctl set-hostname <your-prefix>-doc-writer

# On test server

clawhub install pilot-github-bridge pilot-task-router pilot-audit-log

pilotctl set-hostname <your-prefix>-test-runner

# On coordinator server

clawhub install pilot-github-bridge pilot-task-chain pilot-slack-bridge pilot-broadcast

pilotctl set-hostname <your-prefix>-coordinator

# Establish trust between agents

# Agents are private by default. Each pair that communicates

# must exchange handshakes. When both sides send a handshake,

# trust is auto-approved — no manual step needed.

# On coordinator:

pilotctl handshake <your-prefix>-doc-writer "setup: dev-team-assistants"

# On doc-writer:

pilotctl handshake <your-prefix>-coordinator "setup: dev-team-assistants"

# On coordinator:

pilotctl handshake <your-prefix>-reviewer "setup: dev-team-assistants"

# On reviewer:

pilotctl handshake <your-prefix>-coordinator "setup: dev-team-assistants"

# On coordinator:

pilotctl handshake <your-prefix>-test-runner "setup: dev-team-assistants"

# On test-runner:

pilotctl handshake <your-prefix>-coordinator "setup: dev-team-assistants"

# Verify trust is established

pilotctl trust

ETL Data Pipeline

advanced 5 agents · 14 skills

A five-stage ETL pipeline for production data processing. Agents handle ingestion from S3 and databases, parallel transformation, data validation with quarantine for bad records, loading into target stores, and automated reporting via Slack dashboards.

pilot-s3-bridge pilot-database-bridge pilot-task-chain pilot-cron pilot-task-router pilot-stream-data pilot-task-parallel pilot-audit-log pilot-alert pilot-quarantine pilot-receipt pilot-webhook-bridge pilot-metrics pilot-slack-bridge

Agents 5

<your-prefix>-ingest Data Ingestion

Pulls raw data from S3 buckets and databases on a cron schedule. Stages data for the transform pipeline.

pilot-s3-bridge pilot-database-bridge pilot-task-chain pilot-cron

clawhub install pilot-s3-bridge pilot-database-bridge pilot-task-chain pilot-cron

pilotctl set-hostname <your-prefix>-ingest

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-transform "setup: etl-data-pipeline"

<your-prefix>-transform Data Transformer

Processes raw data in parallel — normalization, enrichment, deduplication. Streams results to the validator.

pilot-task-router pilot-stream-data pilot-task-parallel

clawhub install pilot-task-router pilot-stream-data pilot-task-parallel

pilotctl set-hostname <your-prefix>-transform

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-ingest "setup: etl-data-pipeline"

pilotctl handshake <your-prefix>-validate "setup: etl-data-pipeline"

<your-prefix>-validate Data Validator

Checks data quality, schema conformance, and business rules. Quarantines invalid records and alerts on high error rates.

pilot-task-router pilot-audit-log pilot-alert pilot-quarantine

clawhub install pilot-task-router pilot-audit-log pilot-alert pilot-quarantine

pilotctl set-hostname <your-prefix>-validate

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-loader "setup: etl-data-pipeline"

pilotctl handshake <your-prefix>-reporter "setup: etl-data-pipeline"

pilotctl handshake <your-prefix>-transform "setup: etl-data-pipeline"

<your-prefix>-loader Data Loader

Writes validated data to target databases and data warehouses. Issues receipts for every successful load batch.

pilot-database-bridge pilot-task-chain pilot-receipt

clawhub install pilot-database-bridge pilot-task-chain pilot-receipt

pilotctl set-hostname <your-prefix>-loader

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-reporter "setup: etl-data-pipeline"

pilotctl handshake <your-prefix>-validate "setup: etl-data-pipeline"

<your-prefix>-reporter Pipeline Reporter

Aggregates pipeline metrics, generates dashboards, and sends daily/hourly summaries to Slack. Sends notifications on pipeline issues.

pilot-webhook-bridge pilot-metrics pilot-slack-bridge pilot-cron

clawhub install pilot-webhook-bridge pilot-metrics pilot-slack-bridge pilot-cron

pilotctl set-hostname <your-prefix>-reporter

# Establish trust with peers (both sides must handshake)

pilotctl handshake <your-prefix>-loader "setup: etl-data-pipeline"

pilotctl handshake <your-prefix>-validate "setup: etl-data-pipeline"

Data Flows

<your-prefix>-ingest → <your-prefix>-transform Streams raw data batches for processing :1001

<your-prefix>-transform → <your-prefix>-validate Sends transformed records for validation :1001

<your-prefix>-validate → <your-prefix>-loader Forwards validated records for loading :1001

<your-prefix>-loader → <your-prefix>-reporter Sends load receipts and batch metrics :1002

<your-prefix>-validate → <your-prefix>-reporter Reports validation errors and quarantine counts :1002

Quick Start

# Replace <your-prefix> with a unique name for your deployment (e.g. acme)

# On ingestion server

clawhub install pilot-s3-bridge pilot-database-bridge pilot-task-chain pilot-cron

pilotctl set-hostname <your-prefix>-ingest

# On transform server

clawhub install pilot-task-router pilot-stream-data pilot-task-parallel

pilotctl set-hostname <your-prefix>-transform

# On validation server

clawhub install pilot-task-router pilot-audit-log pilot-alert pilot-quarantine

pilotctl set-hostname <your-prefix>-validate

# On loader server

clawhub install pilot-database-bridge pilot-task-chain pilot-receipt

pilotctl set-hostname <your-prefix>-loader

# On reporting server

clawhub install pilot-webhook-bridge pilot-metrics pilot-slack-bridge pilot-cron

pilotctl set-hostname <your-prefix>-reporter

# Establish trust between agents

# Agents are private by default. Each pair that communicates

# must exchange handshakes. When both sides send a handshake,

# trust is auto-approved — no manual step needed.

# On ingest:

pilotctl handshake <your-prefix>-transform "setup: etl-data-pipeline"

# On transform:

pilotctl handshake <your-prefix>-ingest "setup: etl-data-pipeline"

# On loader:

pilotctl handshake <your-prefix>-reporter "setup: etl-data-pipeline"

# On reporter:

pilotctl handshake <your-prefix>-loader "setup: etl-data-pipeline"

# On loader:

pilotctl handshake <your-prefix>-validate "setup: etl-data-pipeline"

# On validate:

pilotctl handshake <your-prefix>-loader "setup: etl-data-pipeline"

# On reporter:

pilotctl handshake <your-prefix>-validate "setup: etl-data-pipeline"

# On validate:

pilotctl handshake <your-prefix>-reporter "setup: etl-data-pipeline"

# On transform:

pilotctl handshake <your-prefix>-validate "setup: etl-data-pipeline"

# On validate:

pilotctl handshake <your-prefix>-transform "setup: etl-data-pipeline"

# Verify trust is established

pilotctl trust

Swarm Task Farm

advanced 5 agents · 11 skills

A self-organizing compute swarm. Workers join automatically, a leader is elected via consensus, and tasks are distributed using map-reduce. Failed tasks retry automatically. A monitor agent tracks swarm health and reports to Slack.

pilot-leader-election pilot-formation pilot-task-router pilot-broadcast pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics pilot-task-monitor pilot-mesh-status pilot-slack-bridge

Agents 5

<your-prefix>-leader Swarm Leader

Elected via consensus. Accepts incoming tasks, partitions them using map-reduce, and broadcasts work units to workers. Re-election happens automatically if the leader goes down.

pilot-leader-election pilot-formation pilot-task-router pilot-broadcast

clawhub install pilot-leader-election pilot-formation pilot-task-router pilot-broadcast

pilotctl set-hostname <your-prefix>-leader

# Establish trust with all swarm members

pilotctl handshake <your-prefix>-worker-1 "swarm task farm"

pilotctl handshake <your-prefix>-worker-2 "swarm task farm"

pilotctl handshake <your-prefix>-worker-3 "swarm task farm"

pilotctl handshake <your-prefix>-monitor "swarm task farm"

<your-prefix>-worker-1 Compute Worker

Joins the swarm, receives work units, executes tasks, and returns results. Retries failed tasks automatically.

pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics

clawhub install pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics

pilotctl set-hostname <your-prefix>-worker-1

# Trust the leader and monitor

pilotctl handshake <your-prefix>-leader "swarm task farm"

pilotctl handshake <your-prefix>-monitor "swarm task farm"

<your-prefix>-worker-2 Compute Worker

Joins the swarm, receives work units, executes tasks, and returns results. Retries failed tasks automatically.

pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics

clawhub install pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics

pilotctl set-hostname <your-prefix>-worker-2

# Trust the leader and monitor

pilotctl handshake <your-prefix>-leader "swarm task farm"

pilotctl handshake <your-prefix>-monitor "swarm task farm"

<your-prefix>-worker-3 Compute Worker

Joins the swarm, receives work units, executes tasks, and returns results. Retries failed tasks automatically.

pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics

clawhub install pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics

pilotctl set-hostname <your-prefix>-worker-3

# Trust the leader and monitor

pilotctl handshake <your-prefix>-leader "swarm task farm"

pilotctl handshake <your-prefix>-monitor "swarm task farm"

<your-prefix>-monitor Swarm Monitor

Tracks which workers are alive, task completion rates, and queue depth. Alerts on worker failures or stalled tasks.

pilot-task-monitor pilot-mesh-status pilot-slack-bridge pilot-metrics

clawhub install pilot-task-monitor pilot-mesh-status pilot-slack-bridge pilot-metrics

pilotctl set-hostname <your-prefix>-monitor

# Trust leader and all workers

pilotctl handshake <your-prefix>-leader "swarm task farm"

pilotctl handshake <your-prefix>-worker-1 "swarm task farm"

pilotctl handshake <your-prefix>-worker-2 "swarm task farm"

pilotctl handshake <your-prefix>-worker-3 "swarm task farm"

Data Flows

<your-prefix>-leader → <your-prefix>-worker-1 Distributes work units via map-reduce :1002

<your-prefix>-leader → <your-prefix>-worker-2 Distributes work units via map-reduce :1002

<your-prefix>-leader → <your-prefix>-worker-3 Distributes work units via map-reduce :1002

<your-prefix>-worker-1 → <your-prefix>-leader Returns completed results :1002

<your-prefix>-worker-2 → <your-prefix>-leader Returns completed results :1002

<your-prefix>-worker-3 → <your-prefix>-leader Returns completed results :1002

<your-prefix>-worker-1 → <your-prefix>-monitor Reports task metrics and heartbeats :1002

<your-prefix>-worker-2 → <your-prefix>-monitor Reports task metrics and heartbeats :1002

<your-prefix>-worker-3 → <your-prefix>-monitor Reports task metrics and heartbeats :1002

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On leader node

clawhub install pilot-leader-election pilot-formation pilot-task-router pilot-broadcast

pilotctl set-hostname <your-prefix>-leader

# On each worker node (repeat for worker-1, worker-2, worker-3)

clawhub install pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics

pilotctl set-hostname <your-prefix>-worker-1

# On monitor node

clawhub install pilot-task-monitor pilot-mesh-status pilot-slack-bridge pilot-metrics

pilotctl set-hostname <your-prefix>-monitor

# Establish trust between agents

# Each worker must handshake the leader and monitor.

# The leader must handshake all workers and the monitor.

# When both sides handshake, trust is auto-approved.

# On leader:

pilotctl handshake <your-prefix>-worker-1 "swarm task farm"

# On worker-1:

pilotctl handshake <your-prefix>-leader "swarm task farm"

# On leader:

pilotctl handshake <your-prefix>-worker-2 "swarm task farm"

# On worker-2:

pilotctl handshake <your-prefix>-leader "swarm task farm"

# On leader:

pilotctl handshake <your-prefix>-worker-3 "swarm task farm"

# On worker-3:

pilotctl handshake <your-prefix>-leader "swarm task farm"

# On monitor:

pilotctl handshake <your-prefix>-worker-1 "swarm task farm"

# On worker-1:

pilotctl handshake <your-prefix>-monitor "swarm task farm"

# On monitor:

pilotctl handshake <your-prefix>-worker-2 "swarm task farm"

# On worker-2:

pilotctl handshake <your-prefix>-monitor "swarm task farm"

# On monitor:

pilotctl handshake <your-prefix>-worker-3 "swarm task farm"

# On worker-3:

pilotctl handshake <your-prefix>-monitor "swarm task farm"

# Verify trust is established

pilotctl trust

Security Operations Center

advanced 4 agents · 15 skills

A SOC pipeline that collects security events, analyzes patterns, replays incidents for forensics, and enforces blocks automatically. The enforcer maintains a live blocklist and can quarantine compromised nodes. A dashboard agent provides real-time network visibility.

pilot-event-log pilot-audit-log pilot-stream-data pilot-cron pilot-event-filter pilot-event-replay pilot-alert pilot-priority-queue pilot-blocklist pilot-quarantine pilot-webhook-bridge pilot-metrics pilot-slack-bridge pilot-network-map pilot-mesh-status

Agents 4

<your-prefix>-collector Log Collector

Aggregates security events from all nodes — auth failures, connection attempts, anomalous traffic. Streams events to the analyzer in real time.

pilot-event-log pilot-audit-log pilot-stream-data pilot-cron

clawhub install pilot-event-log pilot-audit-log pilot-stream-data pilot-cron

pilotctl set-hostname <your-prefix>-collector

# Trust the analyzer to receive event stream

pilotctl handshake <your-prefix>-analyzer "soc pipeline"

<your-prefix>-analyzer Threat Analyzer

Filters and correlates events, detects attack patterns, classifies threats by severity. Can replay past events for forensic investigation.

pilot-event-filter pilot-event-replay pilot-alert pilot-priority-queue

clawhub install pilot-event-filter pilot-event-replay pilot-alert pilot-priority-queue

pilotctl set-hostname <your-prefix>-analyzer

# Trust collector, enforcer, and dashboard

pilotctl handshake <your-prefix>-collector "soc pipeline"

pilotctl handshake <your-prefix>-enforcer "soc pipeline"

pilotctl handshake <your-prefix>-dashboard "soc pipeline"

<your-prefix>-enforcer Threat Enforcer

Receives threat verdicts and acts — adds IPs to blocklist, quarantines compromised agents, triggers incident webhooks. Maintains a live deny-list.

pilot-blocklist pilot-quarantine pilot-webhook-bridge pilot-audit-log

clawhub install pilot-blocklist pilot-quarantine pilot-webhook-bridge pilot-audit-log

pilotctl set-hostname <your-prefix>-enforcer

# Trust the analyzer and dashboard

pilotctl handshake <your-prefix>-analyzer "soc pipeline"

pilotctl handshake <your-prefix>-dashboard "soc pipeline"

<your-prefix>-dashboard SOC Dashboard

Visualizes network topology, active threats, blocked actors, and overall security posture. Sends summary reports to Slack.

pilot-metrics pilot-slack-bridge pilot-network-map pilot-mesh-status

clawhub install pilot-metrics pilot-slack-bridge pilot-network-map pilot-mesh-status

pilotctl set-hostname <your-prefix>-dashboard

# Trust analyzer and enforcer for status feeds

pilotctl handshake <your-prefix>-analyzer "soc pipeline"

pilotctl handshake <your-prefix>-enforcer "soc pipeline"

Data Flows

<your-prefix>-collector → <your-prefix>-analyzer Streams raw security events :1002

<your-prefix>-analyzer → <your-prefix>-enforcer Sends threat verdicts for enforcement :1002

<your-prefix>-analyzer → <your-prefix>-dashboard Sends classified threats for display :1002

<your-prefix>-enforcer → <your-prefix>-dashboard Reports enforcement actions taken :1002

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On log collection node

clawhub install pilot-event-log pilot-audit-log pilot-stream-data pilot-cron

pilotctl set-hostname <your-prefix>-collector

# On analysis node

clawhub install pilot-event-filter pilot-event-replay pilot-alert pilot-priority-queue

pilotctl set-hostname <your-prefix>-analyzer

# On enforcement node

clawhub install pilot-blocklist pilot-quarantine pilot-webhook-bridge pilot-audit-log

pilotctl set-hostname <your-prefix>-enforcer

# On dashboard node

clawhub install pilot-metrics pilot-slack-bridge pilot-network-map pilot-mesh-status

pilotctl set-hostname <your-prefix>-dashboard

# Establish trust between agents

# collector <-> analyzer, analyzer <-> enforcer,

# analyzer <-> dashboard, enforcer <-> dashboard

# Both sides must handshake for auto-approval.

# On analyzer:

pilotctl handshake <your-prefix>-collector "soc pipeline"

# On collector:

pilotctl handshake <your-prefix>-analyzer "soc pipeline"

# On analyzer:

pilotctl handshake <your-prefix>-dashboard "soc pipeline"

# On dashboard:

pilotctl handshake <your-prefix>-analyzer "soc pipeline"

# On analyzer:

pilotctl handshake <your-prefix>-enforcer "soc pipeline"

# On enforcer:

pilotctl handshake <your-prefix>-analyzer "soc pipeline"

# On dashboard:

pilotctl handshake <your-prefix>-enforcer "soc pipeline"

# On enforcer:

pilotctl handshake <your-prefix>-dashboard "soc pipeline"

# Verify trust is established

pilotctl trust

Knowledge Base (RAG)

intermediate 4 agents · 11 skills

A retrieval-augmented generation pipeline. Documents are ingested from S3 or file shares, chunked and embedded in parallel, indexed into a vector store, and served to query agents. Health checks and load balancing keep the query layer responsive under load.

pilot-s3-bridge pilot-share pilot-task-chain pilot-cron pilot-chunk-transfer pilot-task-parallel pilot-metrics pilot-database-bridge pilot-health pilot-api-gateway pilot-load-balancer

Agents 4

<your-prefix>-rag-ingest Document Ingestion

Pulls documents from S3 buckets or shared directories on a schedule. Chunks large documents and forwards them to the embedder.

pilot-s3-bridge pilot-share pilot-chunk-transfer pilot-cron

clawhub install pilot-s3-bridge pilot-share pilot-chunk-transfer pilot-cron

pilotctl set-hostname <your-prefix>-rag-ingest

# Trust the embedder to receive document chunks

pilotctl handshake <your-prefix>-rag-embedder "rag pipeline"

<your-prefix>-rag-embedder Embedding Generator

Receives document chunks and generates vector embeddings in parallel. Forwards embeddings with metadata to the indexer.

pilot-task-parallel pilot-share pilot-metrics pilot-task-chain

clawhub install pilot-task-parallel pilot-share pilot-metrics pilot-task-chain

pilotctl set-hostname <your-prefix>-rag-embedder

# Trust ingest and indexer

pilotctl handshake <your-prefix>-rag-ingest "rag pipeline"

pilotctl handshake <your-prefix>-rag-indexer "rag pipeline"

<your-prefix>-rag-indexer Vector Indexer

Writes embeddings to the vector database. Maintains indexes and reports ingestion metrics. Serves as the data backend for query agents.

pilot-database-bridge pilot-share pilot-task-chain pilot-health

clawhub install pilot-database-bridge pilot-share pilot-task-chain pilot-health

pilotctl set-hostname <your-prefix>-rag-indexer

# Trust embedder and query server

pilotctl handshake <your-prefix>-rag-embedder "rag pipeline"

pilotctl handshake <your-prefix>-rag-query "rag pipeline"

<your-prefix>-rag-query Query Server

Accepts search queries, retrieves relevant documents from the indexer, and returns ranked results. Load-balanced for high throughput.

pilot-api-gateway pilot-health pilot-load-balancer pilot-metrics

clawhub install pilot-api-gateway pilot-health pilot-load-balancer pilot-metrics

pilotctl set-hostname <your-prefix>-rag-query

# Trust the indexer for retrieval

pilotctl handshake <your-prefix>-rag-indexer "rag pipeline"

Data Flows

<your-prefix>-rag-ingest → <your-prefix>-rag-embedder Sends document chunks for embedding :1001

<your-prefix>-rag-embedder → <your-prefix>-rag-indexer Sends embeddings for indexing :1001

<your-prefix>-rag-query → <your-prefix>-rag-indexer Retrieves relevant documents by similarity :1001

<your-prefix>-rag-indexer → <your-prefix>-rag-query Returns ranked document results :1001

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On ingestion node

clawhub install pilot-s3-bridge pilot-share pilot-chunk-transfer pilot-cron

pilotctl set-hostname <your-prefix>-rag-ingest

# On embedding node (GPU recommended)

clawhub install pilot-task-parallel pilot-share pilot-metrics pilot-task-chain

pilotctl set-hostname <your-prefix>-rag-embedder

# On indexer node

clawhub install pilot-database-bridge pilot-share pilot-task-chain pilot-health

pilotctl set-hostname <your-prefix>-rag-indexer

# On query server

clawhub install pilot-api-gateway pilot-health pilot-load-balancer pilot-metrics

pilotctl set-hostname <your-prefix>-rag-query

# Establish trust: ingest <-> embedder <-> indexer <-> query

# Both sides must handshake for auto-approval.

# On embedder:

pilotctl handshake <your-prefix>-rag-indexer "rag pipeline"

# On indexer:

pilotctl handshake <your-prefix>-rag-embedder "rag pipeline"

# On embedder:

pilotctl handshake <your-prefix>-rag-ingest "rag pipeline"

# On ingest:

pilotctl handshake <your-prefix>-rag-embedder "rag pipeline"

# On indexer:

pilotctl handshake <your-prefix>-rag-query "rag pipeline"

# On query:

pilotctl handshake <your-prefix>-rag-indexer "rag pipeline"

# Verify trust is established

pilotctl trust

Agent Marketplace

advanced 4 agents · 14 skills

A decentralized marketplace where agents advertise their capabilities, a matchmaker pairs requesters with providers, and transactions are settled through escrow. Reputation scores ensure quality. No central platform takes a cut.

pilot-directory pilot-announce-capabilities pilot-discover pilot-reputation pilot-matchmaker pilot-auction pilot-priority-queue pilot-escrow pilot-receipt pilot-audit-log pilot-webhook-bridge pilot-api-gateway pilot-health pilot-metrics

Agents 4

<your-prefix>-directory Capability Directory

Maintains a registry of agent capabilities. Agents announce what they can do, and the directory makes them discoverable. Tracks reputation scores based on completed transactions.

pilot-directory pilot-announce-capabilities pilot-discover pilot-reputation

clawhub install pilot-directory pilot-announce-capabilities pilot-discover pilot-reputation

pilotctl set-hostname <your-prefix>-directory

# Trust matchmaker and gateway

pilotctl handshake <your-prefix>-matchmaker "marketplace"

pilotctl handshake <your-prefix>-gateway "marketplace"

<your-prefix>-matchmaker Request Matchmaker

Receives task requests, queries the directory for capable agents, runs auctions when multiple providers compete, and routes the winning match to escrow.

pilot-matchmaker pilot-auction pilot-priority-queue pilot-audit-log

clawhub install pilot-matchmaker pilot-auction pilot-priority-queue pilot-audit-log

pilotctl set-hostname <your-prefix>-matchmaker

# Trust directory, escrow, and gateway

pilotctl handshake <your-prefix>-directory "marketplace"

pilotctl handshake <your-prefix>-escrow "marketplace"

pilotctl handshake <your-prefix>-gateway "marketplace"

<your-prefix>-escrow Transaction Escrow

Holds task payment in escrow until the provider delivers and the requester confirms. Issues receipts and updates reputation scores on completion.

pilot-escrow pilot-receipt pilot-audit-log pilot-webhook-bridge

clawhub install pilot-escrow pilot-receipt pilot-audit-log pilot-webhook-bridge

pilotctl set-hostname <your-prefix>-escrow

# Trust matchmaker and directory (for reputation updates)

pilotctl handshake <your-prefix>-matchmaker "marketplace"

pilotctl handshake <your-prefix>-directory "marketplace"

<your-prefix>-gateway Marketplace Gateway

Public-facing API gateway. Accepts external requests, load-balances across matchmakers, and serves marketplace health metrics.

pilot-api-gateway pilot-health pilot-load-balancer pilot-metrics

clawhub install pilot-api-gateway pilot-health pilot-load-balancer pilot-metrics

pilotctl set-hostname <your-prefix>-gateway

# Trust directory and matchmaker

pilotctl handshake <your-prefix>-directory "marketplace"

pilotctl handshake <your-prefix>-matchmaker "marketplace"

Data Flows

<your-prefix>-gateway → <your-prefix>-matchmaker Forwards incoming task requests :1002

<your-prefix>-matchmaker → <your-prefix>-directory Queries for capable providers :1002

<your-prefix>-matchmaker → <your-prefix>-escrow Initiates escrow for matched transactions :1002

<your-prefix>-escrow → <your-prefix>-directory Updates reputation after settlement :1002

<your-prefix>-gateway → <your-prefix>-directory Queries capability directory for discovery :1002

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On directory node

clawhub install pilot-directory pilot-announce-capabilities pilot-discover pilot-reputation

pilotctl set-hostname <your-prefix>-directory

# On matchmaker node

clawhub install pilot-matchmaker pilot-auction pilot-priority-queue pilot-audit-log

pilotctl set-hostname <your-prefix>-matchmaker

# On escrow node

clawhub install pilot-escrow pilot-receipt pilot-audit-log pilot-webhook-bridge

pilotctl set-hostname <your-prefix>-escrow

# On gateway node

clawhub install pilot-api-gateway pilot-health pilot-load-balancer pilot-metrics

pilotctl set-hostname <your-prefix>-gateway

# Establish trust between marketplace agents

# gateway <-> matchmaker <-> directory

# matchmaker <-> escrow <-> directory

# Both sides must handshake for auto-approval.

# On directory:

pilotctl handshake <your-prefix>-escrow "marketplace"

# On escrow:

pilotctl handshake <your-prefix>-directory "marketplace"

# On directory:

pilotctl handshake <your-prefix>-matchmaker "marketplace"

# On matchmaker:

pilotctl handshake <your-prefix>-directory "marketplace"

# On escrow:

pilotctl handshake <your-prefix>-matchmaker "marketplace"

# On matchmaker:

pilotctl handshake <your-prefix>-escrow "marketplace"

# On gateway:

pilotctl handshake <your-prefix>-matchmaker "marketplace"

# On matchmaker:

pilotctl handshake <your-prefix>-gateway "marketplace"

# Verify trust is established

pilotctl trust

Backup & Disaster Recovery

intermediate 4 agents · 12 skills

Automated backup infrastructure across multiple sites. A scheduler triggers periodic backups, the primary backup agent compresses and archives data, a secondary site syncs copies for disaster recovery, and a tester periodically restores and verifies backup integrity.

pilot-cron pilot-task-chain pilot-audit-log pilot-slack-bridge pilot-backup pilot-archive pilot-compress pilot-share pilot-sync pilot-verify pilot-health pilot-alert

Agents 4

<your-prefix>-backup-sched Backup Scheduler

Orchestrates the backup lifecycle on a cron schedule. Triggers backups, monitors completion, and sends reports to Slack.

pilot-cron pilot-task-chain pilot-audit-log pilot-slack-bridge

clawhub install pilot-cron pilot-task-chain pilot-audit-log pilot-slack-bridge

pilotctl set-hostname <your-prefix>-backup-sched

# Trust primary and secondary backup agents

pilotctl handshake <your-prefix>-backup-primary "backup dr"

pilotctl handshake <your-prefix>-backup-secondary "backup dr"

pilotctl handshake <your-prefix>-restore-tester "backup dr"

<your-prefix>-backup-primary Primary Backup

Creates backups of databases and file systems. Compresses and archives them locally, then shares with the offsite secondary.

pilot-backup pilot-archive pilot-compress pilot-share

clawhub install pilot-backup pilot-archive pilot-compress pilot-share

pilotctl set-hostname <your-prefix>-backup-primary

# Trust scheduler and secondary

pilotctl handshake <your-prefix>-backup-sched "backup dr"

pilotctl handshake <your-prefix>-backup-secondary "backup dr"

<your-prefix>-backup-secondary Offsite Replica

Receives backup archives from the primary site and syncs them to offsite storage. Verifies integrity checksums and reports health.

pilot-sync pilot-verify pilot-health pilot-share

clawhub install pilot-sync pilot-verify pilot-health pilot-share

pilotctl set-hostname <your-prefix>-backup-secondary

# Trust primary and scheduler

pilotctl handshake <your-prefix>-backup-primary "backup dr"

pilotctl handshake <your-prefix>-backup-sched "backup dr"

pilotctl handshake <your-prefix>-restore-tester "backup dr"

<your-prefix>-restore-tester Restore Tester

Periodically pulls backups from the secondary, attempts a full restore in an isolated environment, and verifies data integrity. Alerts on failures.

pilot-backup pilot-verify pilot-health pilot-alert

clawhub install pilot-backup pilot-verify pilot-health pilot-alert

pilotctl set-hostname <your-prefix>-restore-tester

# Trust secondary and scheduler

pilotctl handshake <your-prefix>-backup-secondary "backup dr"

pilotctl handshake <your-prefix>-backup-sched "backup dr"

Data Flows

<your-prefix>-backup-sched → <your-prefix>-backup-primary Triggers scheduled backup jobs :1002

<your-prefix>-backup-primary → <your-prefix>-backup-secondary Transfers compressed backup archives :1001

<your-prefix>-backup-secondary → <your-prefix>-restore-tester Provides backups for restore testing :1001

<your-prefix>-restore-tester → <your-prefix>-backup-sched Reports restore test results :1002

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On scheduler node

clawhub install pilot-cron pilot-task-chain pilot-audit-log pilot-slack-bridge

pilotctl set-hostname <your-prefix>-backup-sched

# On primary backup server

clawhub install pilot-backup pilot-archive pilot-compress pilot-share

pilotctl set-hostname <your-prefix>-backup-primary

# On offsite secondary (different region/datacenter)

clawhub install pilot-sync pilot-verify pilot-health pilot-share

pilotctl set-hostname <your-prefix>-backup-secondary

# On restore test server

clawhub install pilot-backup pilot-verify pilot-health pilot-alert

pilotctl set-hostname <your-prefix>-restore-tester

# Establish trust along the backup chain

# scheduler <-> primary <-> secondary <-> tester <-> scheduler

# Both sides must handshake for auto-approval.

# On primary:

pilotctl handshake <your-prefix>-backup-sched "backup dr"

# On scheduler:

pilotctl handshake <your-prefix>-backup-primary "backup dr"

# On primary:

pilotctl handshake <your-prefix>-backup-secondary "backup dr"

# On secondary:

pilotctl handshake <your-prefix>-backup-primary "backup dr"

# On scheduler:

pilotctl handshake <your-prefix>-restore-tester "backup dr"

# On tester:

pilotctl handshake <your-prefix>-backup-sched "backup dr"

# On secondary:

pilotctl handshake <your-prefix>-restore-tester "backup dr"

# On tester:

pilotctl handshake <your-prefix>-backup-secondary "backup dr"

# Verify trust is established

pilotctl trust

Chat & Collaboration Hub

intermediate 4 agents · 14 skills

A self-hosted collaboration platform for agent teams. Supports group chat rooms with threaded conversations, real-time presence indicators, automatic message translation, and a moderation bot that filters content and maintains archives.

pilot-group-chat pilot-thread pilot-presence pilot-broadcast pilot-event-filter pilot-blocklist pilot-audit-log pilot-alert pilot-translate pilot-stream-data pilot-task-router pilot-archive pilot-event-log pilot-cron

Agents 4

<your-prefix>-chat Chat Server

Hosts group chat rooms and threaded conversations. Tracks presence (online/away/offline) and broadcasts messages to room participants.

pilot-group-chat pilot-thread pilot-presence pilot-broadcast

clawhub install pilot-group-chat pilot-thread pilot-presence pilot-broadcast

pilotctl set-hostname <your-prefix>-chat

# Trust moderator, translator, and archive bot

pilotctl handshake <your-prefix>-moderator "chat hub"

pilotctl handshake <your-prefix>-translator "chat hub"

pilotctl handshake <your-prefix>-archive-bot "chat hub"

<your-prefix>-moderator Content Moderator

Filters messages for policy violations, spam, and harmful content. Can blocklist abusive agents and alerts admins on serious violations.

pilot-event-filter pilot-blocklist pilot-audit-log pilot-alert

clawhub install pilot-event-filter pilot-blocklist pilot-audit-log pilot-alert

pilotctl set-hostname <your-prefix>-moderator

# Trust chat server

pilotctl handshake <your-prefix>-chat "chat hub"

<your-prefix>-translator Auto-Translator

Translates messages between languages in real time. Streams translated content back to the chat server for delivery to participants.

pilot-translate pilot-stream-data pilot-task-router

clawhub install pilot-translate pilot-stream-data pilot-task-router

pilotctl set-hostname <your-prefix>-translator

# Trust chat server

pilotctl handshake <your-prefix>-chat "chat hub"

<your-prefix>-archive-bot Archive Bot

Archives all conversations for compliance and search. Maintains a searchable event log and runs periodic backup jobs.

pilot-archive pilot-event-log pilot-backup pilot-cron

clawhub install pilot-archive pilot-event-log pilot-backup pilot-cron

pilotctl set-hostname <your-prefix>-archive-bot

# Trust chat server for message stream

pilotctl handshake <your-prefix>-chat "chat hub"

Data Flows

<your-prefix>-chat → <your-prefix>-moderator Sends messages for content filtering :1002

<your-prefix>-chat → <your-prefix>-translator Sends messages for translation :1002

<your-prefix>-translator → <your-prefix>-chat Returns translated messages :1002

<your-prefix>-chat → <your-prefix>-archive-bot Streams all messages for archival :1002

<your-prefix>-moderator → <your-prefix>-chat Sends block/filter actions :1002

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On chat server

clawhub install pilot-group-chat pilot-thread pilot-presence pilot-broadcast

pilotctl set-hostname <your-prefix>-chat

# On moderator node

clawhub install pilot-event-filter pilot-blocklist pilot-audit-log pilot-alert

pilotctl set-hostname <your-prefix>-moderator

# On translator node

clawhub install pilot-translate pilot-stream-data pilot-task-router

pilotctl set-hostname <your-prefix>-translator

# On archive node

clawhub install pilot-archive pilot-event-log pilot-backup pilot-cron

pilotctl set-hostname <your-prefix>-archive-bot

# Establish trust — all agents trust the chat server

# The chat server must handshake each agent, and each agent

# must handshake the chat server. Auto-approved when mutual.

# On archive-bot:

pilotctl handshake <your-prefix>-chat "chat hub"

# On chat-server:

pilotctl handshake <your-prefix>-archive-bot "chat hub"

# On chat-server:

pilotctl handshake <your-prefix>-moderator "chat hub"

# On moderator:

pilotctl handshake <your-prefix>-chat "chat hub"

# On chat-server:

pilotctl handshake <your-prefix>-translator "chat hub"

# On translator:

pilotctl handshake <your-prefix>-chat "chat hub"

# Verify trust is established

pilotctl trust

MCP Bridge Fleet

beginner 3 agents · 11 skills

Bridge different agent ecosystems over Pilot tunnels. An MCP gateway exposes MCP-compatible tool servers, an A2A bridge connects Google A2A agents, and a tool registry lets agents discover available capabilities across protocols. All traffic is encrypted and trust-gated.

pilot-mcp-bridge pilot-api-gateway pilot-health pilot-metrics pilot-a2a-bridge pilot-task-router pilot-audit-log pilot-directory pilot-discover pilot-announce-capabilities pilot-load-balancer

Agents 3

<your-prefix>-mcp-gw MCP Gateway

Bridges MCP tool servers onto the Pilot network. Agents can call MCP tools through encrypted tunnels without exposing HTTP endpoints.

pilot-mcp-bridge pilot-api-gateway pilot-health pilot-metrics

clawhub install pilot-mcp-bridge pilot-api-gateway pilot-health pilot-metrics

pilotctl set-hostname <your-prefix>-mcp-gw

# Trust the tool registry

pilotctl handshake <your-prefix>-tool-registry "mcp bridge fleet"

<your-prefix>-a2a-bridge A2A Bridge

Connects Google A2A protocol agents to the Pilot network. Routes tasks between A2A and Pilot agents transparently.

pilot-a2a-bridge pilot-task-router pilot-audit-log

clawhub install pilot-a2a-bridge pilot-task-router pilot-audit-log

pilotctl set-hostname <your-prefix>-a2a-bridge

# Trust the tool registry

pilotctl handshake <your-prefix>-tool-registry "mcp bridge fleet"

<your-prefix>-tool-registry Tool Registry

Central directory where MCP tools, A2A agents, and native Pilot skills register their capabilities. Other agents query it to discover what tools are available.

pilot-directory pilot-discover pilot-announce-capabilities pilot-load-balancer

clawhub install pilot-directory pilot-discover pilot-announce-capabilities pilot-load-balancer

pilotctl set-hostname <your-prefix>-tool-registry

# Trust both bridge agents

pilotctl handshake <your-prefix>-mcp-gw "mcp bridge fleet"

pilotctl handshake <your-prefix>-a2a-bridge "mcp bridge fleet"

Data Flows

<your-prefix>-mcp-gw → <your-prefix>-tool-registry Registers available MCP tools :1002

<your-prefix>-a2a-bridge → <your-prefix>-tool-registry Registers available A2A agents :1002

<your-prefix>-tool-registry → <your-prefix>-mcp-gw Routes tool calls to MCP servers :1002

<your-prefix>-tool-registry → <your-prefix>-a2a-bridge Routes tasks to A2A agents :1002

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On MCP gateway node

clawhub install pilot-mcp-bridge pilot-api-gateway pilot-health pilot-metrics

pilotctl set-hostname <your-prefix>-mcp-gw

# On A2A bridge node

clawhub install pilot-a2a-bridge pilot-task-router pilot-audit-log

pilotctl set-hostname <your-prefix>-a2a-bridge

# On tool registry node

clawhub install pilot-directory pilot-discover pilot-announce-capabilities pilot-load-balancer

pilotctl set-hostname <your-prefix>-tool-registry

# Establish trust — both bridges trust the registry

# Each bridge handshakes the registry, and the registry

# handshakes each bridge. Auto-approved when mutual.

# On a2a-bridge:

pilotctl handshake <your-prefix>-tool-registry "mcp bridge fleet"

# On tool-registry:

pilotctl handshake <your-prefix>-a2a-bridge "mcp bridge fleet"

# On mcp-gateway:

pilotctl handshake <your-prefix>-tool-registry "mcp bridge fleet"

# On tool-registry:

pilotctl handshake <your-prefix>-mcp-gw "mcp bridge fleet"

# Verify trust is established

pilotctl trust

Compliance & Governance

advanced 4 agents · 15 skills

Automated compliance for regulated environments. A policy engine evaluates every agent action against governance rules, an auditor maintains tamper-evident logs, a certifier issues and verifies compliance certificates, and a reporter generates audit reports on schedule.

pilot-event-filter pilot-sla pilot-workflow pilot-task-chain pilot-audit-log pilot-verify pilot-event-log pilot-cron pilot-certificate pilot-keychain pilot-receipt pilot-metrics pilot-webhook-bridge pilot-slack-bridge pilot-archive

Agents 4

<your-prefix>-policy Policy Engine

Evaluates agent actions against governance rules and SLA policies. Blocks non-compliant actions and routes violations to the auditor.

pilot-event-filter pilot-sla pilot-workflow pilot-task-chain

clawhub install pilot-event-filter pilot-sla pilot-workflow pilot-task-chain

pilotctl set-hostname <your-prefix>-policy

# Trust auditor and certifier

pilotctl handshake <your-prefix>-auditor "compliance"

pilotctl handshake <your-prefix>-certifier "compliance"

<your-prefix>-auditor Audit Trail

Maintains tamper-evident, append-only logs of all agent actions. Runs periodic integrity checks and flags anomalies.

pilot-audit-log pilot-verify pilot-event-log pilot-cron

clawhub install pilot-audit-log pilot-verify pilot-event-log pilot-cron

pilotctl set-hostname <your-prefix>-auditor

# Trust policy engine and reporter

pilotctl handshake <your-prefix>-policy "compliance"

pilotctl handshake <your-prefix>-reporter "compliance"

<your-prefix>-certifier Compliance Certifier

Issues compliance certificates to agents that pass policy checks. Manages a keychain for certificate signing and issues receipts for every certification.

pilot-certificate pilot-keychain pilot-verify pilot-receipt

clawhub install pilot-certificate pilot-keychain pilot-verify pilot-receipt

pilotctl set-hostname <your-prefix>-certifier

# Trust policy engine and reporter

pilotctl handshake <your-prefix>-policy "compliance"

pilotctl handshake <your-prefix>-reporter "compliance"

<your-prefix>-reporter Compliance Reporter

Generates periodic compliance reports from audit logs and certification data. Archives reports and sends summaries to stakeholders via Slack and webhooks.

pilot-metrics pilot-webhook-bridge pilot-slack-bridge pilot-archive

clawhub install pilot-metrics pilot-webhook-bridge pilot-slack-bridge pilot-archive

pilotctl set-hostname <your-prefix>-reporter

# Trust auditor and certifier for report data

pilotctl handshake <your-prefix>-auditor "compliance"

pilotctl handshake <your-prefix>-certifier "compliance"

Data Flows

<your-prefix>-policy → <your-prefix>-auditor Sends policy violations and action logs :1002

<your-prefix>-policy → <your-prefix>-certifier Requests compliance certification for passing agents :1002

<your-prefix>-auditor → <your-prefix>-reporter Provides audit data for reports :1002

<your-prefix>-certifier → <your-prefix>-reporter Provides certification records for reports :1002

Quick Start

# Replace <your-prefix> with a unique name (e.g. acme)

# On policy engine node

clawhub install pilot-event-filter pilot-sla pilot-workflow pilot-task-chain

pilotctl set-hostname <your-prefix>-policy

# On auditor node

clawhub install pilot-audit-log pilot-verify pilot-event-log pilot-cron

pilotctl set-hostname <your-prefix>-auditor

# On certifier node

clawhub install pilot-certificate pilot-keychain pilot-verify pilot-receipt

pilotctl set-hostname <your-prefix>-certifier

# On reporter node

clawhub install pilot-metrics pilot-webhook-bridge pilot-slack-bridge pilot-archive

pilotctl set-hostname <your-prefix>-reporter

# Establish trust

# policy <-> auditor, policy <-> certifier

# auditor <-> reporter, certifier <-> reporter

# Both sides must handshake for auto-approval.

# On auditor:

pilotctl handshake <your-prefix>-policy "compliance"

# On policy-engine:

pilotctl handshake <your-prefix>-auditor "compliance"

# On auditor:

pilotctl handshake <your-prefix>-reporter "compliance"

# On reporter:

pilotctl handshake <your-prefix>-auditor "compliance"

# On certifier:

pilotctl handshake <your-prefix>-policy "compliance"

# On policy-engine:

pilotctl handshake <your-prefix>-certifier "compliance"

# On certifier:

pilotctl handshake <your-prefix>-reporter "compliance"

# On reporter:

pilotctl handshake <your-prefix>-certifier "compliance"

# Verify trust is established

pilotctl trust

Agents are private by default

Build your own setup